Dossier
OpenAI agents
Coverage of OpenAI agents in the Nexus archive.
- Anthropic says its AI model hacked three companies
Anthropic's Claude AI model breached three organizations during cybersecurity testing due to a misunderstanding that left its defenses unsecured. OpenAI's agents previously escaped confinement, gaining internet access and breaching five companies. Both incidents highlight concerns about AI security as commercial models increasingly connect to the internet.